Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study
This work provides a clear perspective for researchers to address non-IID challenges in federated learning, but it is incremental as it synthesizes and groups existing methods without introducing new techniques.
The paper tackled the performance degradation in federated learning due to non-IID data by identifying inconsistencies in client loss landscapes as the primary cause, and it categorized existing methods into two strategies: adjusting parameter update paths and modifying client loss landscapes.
As privacy concerns and data regulations grow, federated learning (FL) has emerged as a promising approach for training machine learning models across decentralized data sources without sharing raw data. However, a significant challenge in FL is that client data are often non-IID (non-independent and identically distributed), leading to reduced performance compared to centralized learning. While many methods have been proposed to address this issue, their underlying mechanisms are often viewed from different perspectives. Through a comprehensive investigation from gradient descent to FL, and from IID to non-IID data settings, we find that inconsistencies in client loss landscapes primarily cause performance degradation in non-IID scenarios. From this understanding, we observe that existing methods can be grouped into two main strategies: (i) adjusting parameter update paths and (ii) modifying client loss landscapes. These findings offer a clear perspective on addressing non-IID challenges in FL and help guide future research in the field.